© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 4838
    Prev
    Next
    INDEX
    Explanations

    words that appear to be prefixes or suffixes of longer words

    oai_token-act-pair · gemini-2.0-flash

    "er"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    richTextPanel
    -0.64
    MENAFN
    -0.59
    DockStyle
    -0.55
    Abp
    -0.55
    BeginContext
    -0.52
    CloseOperation
    -0.52
     ujednoznacz
    -0.51
    IsContent
    -0.49
    VIAF
    -0.48
    isks
    -0.48
    POSITIVE LOGITS
     er
    1.18
    Er
    0.98
    er
    0.96
     Er
    0.93
    ER
    0.93
     ER
    0.90
    ers
    0.90
    ér
    0.90
     ers
    0.88
    erd
    0.88
    Activations Density 1.424%

    No Known Activations